KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Rong, Cai, Pinlong, Mei, Jianbiao, Wen, Licheng, Hu, Tao, Yang, Xuemeng, Fu, Daocheng, Shi, Botian
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909855432835072
author Wu, Rong
Cai, Pinlong
Mei, Jianbiao
Wen, Licheng
Hu, Tao
Yang, Xuemeng
Fu, Daocheng
Shi, Botian
author_facet Wu, Rong
Cai, Pinlong
Mei, Jianbiao
Wen, Licheng
Hu, Tao
Yang, Xuemeng
Fu, Daocheng
Shi, Botian
contents Large language models (LLMs) have made remarkable strides in various natural language processing tasks, but their performance on complex reasoning problems remains hindered by a lack of explainability and trustworthiness. This issue, often manifesting as hallucinations or unattributable reasoning processes, limits their applicability in complex reasoning scenarios. To address this, we propose Knowledge Graph-constrained Trajectory Reasoning Attribution and Chain Explanation Supervision (KG-TRACES), a novel framework that enhances the reasoning ability of LLMs through explicit supervision over reasoning paths and processes. KG-TRACES jointly supervises the model to: (1) predict symbolic relation paths, (2) predict full triple-level reasoning paths, and (3) generate attribution-aware reasoning processes grounded in the reasoning paths. At inference phase, the model adapts to both KG-available and KG-unavailable scenarios, retrieving reasoning paths from a KG when possible or predicting plausible reasoning paths with only intrinsic knowledge when not. This design enables the model to reason in an explainable and source-attributable pattern. Through extensive experiments on complex reasoning tasks, we demonstrate that KG-TRACES significantly outperforms existing SOTA: it improves Hits@1 by 1.6% and F1 by 4.7% on WebQSP, and achieves improvements of 4.8% in Hits@1 and 2.1% in F1 on CWQ. Moreover, we show its transferability to specialized domains such as medicine. By visualizing the intermediate steps of reasoning processes, we further show that the explicit supervision introduced by KG-TRACES leads to more stable and goal-directed reasoning processes, aligning closely with correct answers. Code is available at https://github.com/Edaizi/KG-TRACES.
format Preprint
id arxiv_https___arxiv_org_abs_2506_00783
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision
Wu, Rong
Cai, Pinlong
Mei, Jianbiao
Wen, Licheng
Hu, Tao
Yang, Xuemeng
Fu, Daocheng
Shi, Botian
Computation and Language
Artificial Intelligence
Large language models (LLMs) have made remarkable strides in various natural language processing tasks, but their performance on complex reasoning problems remains hindered by a lack of explainability and trustworthiness. This issue, often manifesting as hallucinations or unattributable reasoning processes, limits their applicability in complex reasoning scenarios. To address this, we propose Knowledge Graph-constrained Trajectory Reasoning Attribution and Chain Explanation Supervision (KG-TRACES), a novel framework that enhances the reasoning ability of LLMs through explicit supervision over reasoning paths and processes. KG-TRACES jointly supervises the model to: (1) predict symbolic relation paths, (2) predict full triple-level reasoning paths, and (3) generate attribution-aware reasoning processes grounded in the reasoning paths. At inference phase, the model adapts to both KG-available and KG-unavailable scenarios, retrieving reasoning paths from a KG when possible or predicting plausible reasoning paths with only intrinsic knowledge when not. This design enables the model to reason in an explainable and source-attributable pattern. Through extensive experiments on complex reasoning tasks, we demonstrate that KG-TRACES significantly outperforms existing SOTA: it improves Hits@1 by 1.6% and F1 by 4.7% on WebQSP, and achieves improvements of 4.8% in Hits@1 and 2.1% in F1 on CWQ. Moreover, we show its transferability to specialized domains such as medicine. By visualizing the intermediate steps of reasoning processes, we further show that the explicit supervision introduced by KG-TRACES leads to more stable and goal-directed reasoning processes, aligning closely with correct answers. Code is available at https://github.com/Edaizi/KG-TRACES.
title KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2506.00783